CVE-2026-34159 json
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
published 2026-04-01 7 mo ago modified 2026-10-26 13 d ago also EUVD-2026-17975
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.6%
- EPSS 1.6% chance of exploitation in 30 days, percentile 76%
- public exploits
- 0
- none known
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticated attacker can read and write arbitrary process memory via crafted GRAPH_COMPUTE messages. Combined with pointer leaks from ALLOC_BUFFER/BUFFER_GET_BASE, this gives full ASLR bypass and remote code execution. No authentication required, just TCP access to the RPC server port. This issue has been patched in version b8492.
Patch / fix
- ggerganov llama.cpp b8492
- ggml llama.cpp b8492
- llama.cpp Debian 14 8611+dfsg-1
debian advisories DEBIAN-CVE-2026-34159
- github.com/ggml-org/llama.cpp@39bf0d3 commit
- github.com/ggml-org/llama.cpp#20908 pull request
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-34159 updated cvss 9.8
llama.cpp: unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
-
Red Hat All currently supported Red Hat productsnot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 7 mo ago
Exploit prediction
1.62% chance of exploitation in the next 30 days, higher than 76% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected products
- ggml-org llama.cpp
Classification
- Weakness
-
- CWE-119 Improper Restriction of Operations within the Bounds of a Memory Buffer
References
-
github.com
/ggml-org/llama.cpp/pull/20908
issue-tracking, patch
-
github.com
/ggml-org/llama.cpp/commit/39bf0d3c6a95803e0f41aaba069ffbee26721042
patch
-
github.com
/ggml-org/llama.cpp/security/advisories/GHSA-j8rj-fmpv-wcxw
exploit, vendor-advisory
Sources
- CVE List CVE-2026-34159
- NVD CVE-2026-34159
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.